Implements FED-010: Agent Spawn via Federation feature that enables spawning and managing Claude agents on remote federated Mosaic Stack instances via COMMAND message type. Features: - Federation agent command types (spawn, status, kill) - FederationAgentService for handling agent operations - Integration with orchestrator's agent spawner/lifecycle services - API endpoints for spawning, querying status, and killing agents - Full command routing through federation COMMAND infrastructure - Comprehensive test coverage (12/12 tests passing) Architecture: - Hub → Spoke: Spawn agents on remote instances - Command flow: FederationController → FederationAgentService → CommandService → Remote Orchestrator - Response handling: Remote orchestrator returns agent status/results - Security: Connection validation, signature verification Files created: - apps/api/src/federation/types/federation-agent.types.ts - apps/api/src/federation/federation-agent.service.ts - apps/api/src/federation/federation-agent.service.spec.ts Files modified: - apps/api/src/federation/command.service.ts (agent command routing) - apps/api/src/federation/federation.controller.ts (agent endpoints) - apps/api/src/federation/federation.module.ts (service registration) - apps/orchestrator/src/api/agents/agents.controller.ts (status endpoint) - apps/orchestrator/src/api/agents/agents.module.ts (lifecycle integration) Testing: - 12/12 tests passing for FederationAgentService - All command service tests passing - TypeScript compilation successful - Linting passed Refs #93 Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
3.5 KiB
3.5 KiB
name, description, homepage, metadata
| name | description | homepage | metadata | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| mosaic-brain | Capture ideas, brain dumps, and semantic search across your Mosaic Stack knowledge base. | https://mosaicstack.dev |
|
Mosaic Brain
Capture and search ideas, brain dumps, and notes in your Mosaic Stack workspace. Provides quick capture, semantic search, and tag management.
Setup
-
Ensure Mosaic Stack API is running (default:
http://localhost:3001) -
Set environment variables:
export MOSAIC_API_URL="http://localhost:3001" export MOSAIC_WORKSPACE_ID="your-workspace-uuid" export MOSAIC_API_TOKEN="your-auth-token" -
Optionally create
~/.config/mosaic/brain.conf:MOSAIC_API_URL=http://localhost:3001 MOSAIC_WORKSPACE_ID=your-workspace-uuid MOSAIC_API_TOKEN=your-auth-token
Common Commands
Quick Brain Dump
Capture an idea quickly without thinking about categorization:
# Quick capture
./brain.sh capture "Had a great idea about using AI for code reviews"
# Capture with title
./brain.sh capture "Remember to follow up with the team about the new feature" --title "Team Follow-up"
Create Detailed Idea
Create an idea with full metadata:
./brain.sh create \
--title "New Feature Idea" \
--content "Implement semantic search across all documents..." \
--tags "feature,ai,search" \
--category "product"
Semantic Search
Search your brain using natural language:
# Query your knowledge base
./brain.sh query "What did I say about AI and code reviews?"
# Search with limit
./brain.sh search "project ideas" --limit 10
List Ideas
# List recent ideas
./brain.sh list
# List with filters
./brain.sh list --limit 20 --tags "work,urgent"
Get Specific Idea
./brain.sh get <idea-id>
Update Idea
./brain.sh update <idea-id> \
--title "Updated Title" \
--tags "new,tags" \
--status "IN_PROGRESS"
Delete Idea
./brain.sh delete <idea-id>
Tag Management
# List all tags
./brain.sh tags
# Add tags to an idea
./brain.sh update <idea-id> --add-tags "urgent,review"
# Remove tags from an idea
./brain.sh update <idea-id> --remove-tags "old-tag"
API Endpoints
The skill uses these Mosaic Stack API endpoints:
- POST /api/ideas/capture - Quick brain dump (minimal fields)
- POST /api/ideas - Create full idea with metadata
- GET /api/ideas - List ideas with filters
- GET /api/ideas/:id - Get specific idea
- PATCH /api/ideas/:id - Update idea
- DELETE /api/ideas/:id - Delete idea
- POST /api/brain/query - Semantic search/query
- GET /api/brain/search - Search ideas
Configuration
Config file priority:
- Environment variables
~/.config/mosaic/brain.conf- Default values
Required settings:
MOSAIC_API_URL- API base URL (default: http://localhost:3001)MOSAIC_WORKSPACE_ID- Your workspace UUIDMOSAIC_API_TOKEN- Authentication token
Usage from Clawdbot
Natural language examples:
- "Remember this..." / "Note to self..." → Quick capture
- "What did I say about..." → Semantic search
- "Show me my recent ideas" → List ideas
- "Brain dump: [content]" → Quick capture
Notes
- Quick capture (
capture) is fastest - just dump your thought - Semantic search (
query) uses AI to find relevant ideas - Regular search is keyword-based, faster but less intelligent
- Tags are automatically indexed for quick filtering
- Ideas support markdown formatting in content